INDEX

Explanations

words related to actions or interactions

oai_token-act-pair · gpt-3.5-turbo

instances of actions and movements described in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ovi

-0.71

irable

-0.65

hare

-0.64

senal

-0.59

represented

-0.59

 occupant

-0.58

 Mali

-0.58

uded

-0.58

 Mold

-0.57

 Contributions

-0.57

POSITIVE LOGITS

 cautiously

0.99

yss

0.90

 reluctantly

0.84

 nervously

0.84

 instinctively

0.80

 aback

0.75

agall

0.75

 realise

0.74

 wondering

0.73

 quizz

0.73

Activations Density 0.307%

words related to actions or interactions

instances of actions and movements described in the text

No Comments

No Known Activations